open-webui / open-webui

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
https://openwebui.com
MIT License
43.98k stars 5.33k forks source link

Unable to upload epub files do workspace - documents #4939

Closed correajl closed 1 month ago

correajl commented 1 month ago

Bug Report

Installation Method

docker run --rm -p 3000:8080 --gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:ollama'

Environment

Expected Behavior:

Upload epub files to be used with RAG, for example. I was using that but after upgrade to last release I couln't upload those file anymore.

Actual Behavior:

When I try to upload epub files I got the following error:

Something went wrong :/ ** Resource punkt_tab not found. Please use the NLTK Downloader to obtain the resource: >>> import nltk >>> nltk.download('punkt_tab')  For more information see: https://www.nltk.org/data.html Attempted to load tokenizers/punkt_tab/english/ Searched in: - '/root/nltk_data' - '/usr/local/nltk_data' - '/usr/local/share/nltk_data' - '/usr/local/lib/nltk_data' - '/usr/share/nltk_data' - '/usr/local/share/nltk_data' - '/usr/lib/nltk_data' - '/usr/local/lib/nltk_data' **

Tried with pdf format and it worked.

Description

Bug Summary: Something got wrong when uploading epub files in workspace > documents.

Reproduction Details

Steps to Reproduce: Run the docker bundle with open-webui + ollama. Create a new user, log in, go to workspace -> documents. Try to upload a epub file.

Logs and Screenshots

Something went wrong :/ ** Resource punkt_tab not found. Please use the NLTK Downloader to obtain the resource: >>> import nltk >>> nltk.download('punkt_tab')  For more information see: https://www.nltk.org/data.html Attempted to load tokenizers/punkt_tab/english/ Searched in: - '/root/nltk_data' - '/usr/local/nltk_data' - '/usr/local/share/nltk_data' - '/usr/local/lib/nltk_data' - '/usr/share/nltk_data' - '/usr/local/share/nltk_data' - '/usr/lib/nltk_data' - '/usr/local/lib/nltk_data' **

Additional Information

I was using a release from some weeks ago and everything was working normally. When I recreate the container with the lastest version I started to get this error.

tjbck commented 1 month ago

Should be fixed on dev!